{"id":"https://openalex.org/W2800664709","doi":"https://doi.org/10.1109/icassp.2018.8462505","title":"CBLDNN-Based Speaker-Independent Speech Separation Via Generative Adversarial Training","display_name":"CBLDNN-Based Speaker-Independent Speech Separation Via Generative Adversarial Training","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2800664709","doi":"https://doi.org/10.1109/icassp.2018.8462505","mag":"2800664709"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462505","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462505","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101744663","display_name":"Chenxing Li","orcid":"https://orcid.org/0009-0001-4226-7825"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenxing Li","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, P.R.China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, P.R.China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100394072","display_name":"Lei Zhu","orcid":"https://orcid.org/0000-0003-1685-7968"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Zhu","raw_affiliation_strings":["AI Lab, Rokid Inc., Beijing, P.R.China"],"affiliations":[{"raw_affiliation_string":"AI Lab, Rokid Inc., Beijing, P.R.China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004363895","display_name":"Shuang Xu","orcid":"https://orcid.org/0000-0003-3576-6914"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, P.R.China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, P.R.China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106667221","display_name":"Peng Gao","orcid":"https://orcid.org/0009-0005-7881-712X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Gao","raw_affiliation_strings":["AI Lab, Rokid Inc., Beijing, P.R.China"],"affiliations":[{"raw_affiliation_string":"AI Lab, Rokid Inc., Beijing, P.R.China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108642431","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0002-1111-1529"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, P.R.China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, P.R.China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101744663"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":4.7891,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.95882782,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"711","last_page":"715"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8003780841827393},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7628675699234009},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.6889966726303101},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43376877903938293},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.43068578839302063},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4285314083099365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4136575758457184},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3736068606376648},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.13533413410186768},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.09160217642784119}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8003780841827393},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7628675699234009},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.6889966726303101},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43376877903938293},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.43068578839302063},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4285314083099365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4136575758457184},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3736068606376648},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.13533413410186768},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.09160217642784119},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462505","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462505","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.47999998927116394,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W185399533","https://openalex.org/W1482149378","https://openalex.org/W1524333225","https://openalex.org/W1550027367","https://openalex.org/W1600744878","https://openalex.org/W2069681747","https://openalex.org/W2075606107","https://openalex.org/W2111070087","https://openalex.org/W2117130368","https://openalex.org/W2124149378","https://openalex.org/W2127851351","https://openalex.org/W2147174722","https://openalex.org/W2155273149","https://openalex.org/W2221409856","https://openalex.org/W2271840356","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2593414223","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2962715207","https://openalex.org/W2963073614","https://openalex.org/W2963341071","https://openalex.org/W2963470893","https://openalex.org/W4320013936","https://openalex.org/W6607486085","https://openalex.org/W6631362777","https://openalex.org/W6635768407","https://openalex.org/W6688843265"],"related_works":["https://openalex.org/W2401567014","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2538939196","https://openalex.org/W2249138175","https://openalex.org/W4313854686","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466"],"abstract_inverted_index":{"In":[0,47],"this":[1],"paper,":[2],"we":[3,51],"propose":[4],"a":[5,42,64],"speaker-independent":[6],"multi-speaker":[7],"monaural":[8],"speech":[9,36,74,77,94],"separation":[10],"system":[11,31],"(CBLDNN-GAT)":[12],"based":[13],"on":[14,103],"convolutional,":[15],"bidirectional":[16],"long":[17],"short-term":[18],"memory,":[19],"deep":[20],"feedforward":[21],"neural":[22],"network":[23],"(CBLDNN)":[24],"with":[25],"generative":[26],"adversarial":[27],"training":[28],"(GAT).":[29],"Our":[30],"aims":[32],"at":[33],"obtaining":[34],"better":[35],"quality":[37,78],"instead":[38],"of":[39],"only":[40],"minimizing":[41],"mean":[43],"square":[44],"error":[45],"(MSE).":[46],"the":[48,68,82,88,92,97,111,122],"initial":[49],"phase,":[50],"utilize":[52],"log-mel":[53],"filterbank":[54],"and":[55,75],"pitch":[56],"features":[57],"to":[58,72],"warm":[59],"up":[60],"our":[61],"CBLDNN":[62],"in":[63],"multi-task":[65],"manner.":[66],"Thus,":[67],"information":[69],"that":[70,110],"contributes":[71],"separating":[73],"improving":[76],"is":[79,121],"integrated":[80],"into":[81],"model.":[83],"We":[84,100],"execute":[85],"GAT":[86],"throughout":[87],"training,":[89],"which":[90,120],"makes":[91],"separated":[93],"indistinguishable":[95],"from":[96],"real":[98],"one.":[99],"evaluate":[101],"CBLDNN-GAT":[102],"WSJ0-2mix":[104],"dataset.":[105],"The":[106],"experimental":[107],"results":[108],"show":[109],"proposed":[112],"model":[113],"achieves":[114],"11.0d-B":[115],"signal-to-distortion":[116],"ratio":[117],"(SDR)":[118],"improvement,":[119],"new":[123],"state-of-the-art":[124],"result.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}